AI Paper Atlas

Research map / Vision-language and multimodal / CLIP and zero-shot

AutoV: Loss-Oriented Ranking for Visual Prompt Retrieval in LVLMs

Yuan Zhang, Chun-Kai Fan, Sicheng Yu, Junwen Pan, Tao Huang, Ming Lu, Kuan Cheng, Qi She, Shanghang Zhang

ECCV 2026 · Vision-language and multimodal › CLIP and zero-shot · approach: Prompt learning for CLIP · 7 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
retrieve a visual prompt with AutoVLLaVA-OneVision 7B · VizWizscore: 58.2 -> 68.4Improved
retrieve a visual prompt with AutoVQwen2.5-VL 7B · MMMUscore: 50.1 -> 53.9Improved
fixed FGVP promptLLaVA-1.5 7B · TextVQAscore: 58.2 -> 46.3Hurt
pairwise ranking instead of regression (ablation)AutoV · MMMU (LLaVA-1.5 7B)score: 36.9 -> 38.7Improved
pairwise instead of list-wise ranking (ablation)AutoV · MMMU (LLaVA-1.5 7B)score: 38.0 -> 38.7Improved
pairwise ranking instead of MoE GateNet (ablation)AutoV · MMMU (LLaVA-1.5 7B)score: 37.6 -> 38.7Improved
random retrieval vs baseline (ablation)AutoV pool · Avg of MMMU/VizWiz/MMVetscore: +0.7Improved
use 0th LLM layer for modality interaction instead of 24th (ablation)AutoV · MMMU (LLaVA-1.5 7B)score: 38.1 -> 38.7Improved
add pre-filtering of farthest prompt (6 candidates) (ablation)AutoV · MMMU (LLaVA-1.5 7B)score: 38.3 -> 38.7Improved
add pre-filtering (8 candidates) (ablation)AutoV · MMMU (LLaVA-1.5 7B)score: 38.4 -> 38.9Improved
enlarge candidate pool from 6 to 7 prompts (ablation)AutoV · MMMU (LLaVA-1.5 7B)score: 38.7 -> 38.7No clear effect
enlarge candidate pool from 1 to 8 prompts (ablation)AutoV · Avg of MMMU/VizWiz/MMVetscore: 39.8 -> 41.6Improved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy